© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 55347
    Prev
    Next
    INDEX
    Explanations

    above to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arti
    -0.07
    ange
    -0.07
    Fa
    -0.07
     movable
    -0.06
     Reader
    -0.06
    å¼ı
    -0.06
    emes
    -0.06
     Ryan
    -0.06
    uve
    -0.06
    umont
    -0.06
    POSITIVE LOGITS
     ];
    0.12
    gate
    0.11
    Gate
    0.11
     favicon
    0.10
    essler
    0.10
     Cyr
    0.10
    ifer
    0.10
    _bd
    0.10
    PEAR
    0.10
    ifr
    0.09
    Activations Density 0.001%

    No Known Activations